[PATCH V3] rs6000: Enhance lowpart/highpart DI->SF by mtvsrws/mtvsrd

[PATCH V3] rs6000: Enhance lowpart/highpart DI->SF by mtvsrws/mtvsrd

[Jiufu Guo]

Hi,

As mentioned in PR108338, on p9, we could use mtvsrws to implement
the bitcast from SI#0 to SF (or lowpart DI to SF).

For code:
  *(long long*)buff = di;
  float f = *(float*)(buff);

"sldi 9,3,32 ; mtvsrd 1,9 ; xscvspdpn 1,1" is generated.
But "mtvsrws 1,3 ; xscvspdpn 1,1" would be better.

Or say, the bitcast from lowpart DI(also highpart DI) to SF could be enhanced.

Compare with previous version:
https://gcc.gnu.org/pipermail/gcc-patches/2023-February/611823.html
This patch does not define new insn for mtvsrws, but use existing insns.


Bootstrap and regtests pass on ppc64{,le}.
Is this ok for trunk?

BR,
Jeff (Jiufu)


	PR target/108338

gcc/ChangeLog:

	* config/rs6000/predicates.md (lowpart_subreg_operator): New
	define_predicate.
	* config/rs6000/rs6000.md (any_rshift): New code_iterator.
	(movsf_from_si): Update to generate mtvsrws for P9.
	(movsf_from_si2): Rename to...
	(movsf_from_si2_<code>): ... this, and use lowpart_subreg_operator.

gcc/testsuite/ChangeLog:

	* gcc.target/powerpc/pr108338.c: New test.

---
 gcc/config/rs6000/predicates.md             |  5 +++
 gcc/config/rs6000/rs6000.md                 | 34 +++++++++++------
 gcc/testsuite/gcc.target/powerpc/pr108338.c | 42 +++++++++++++++++++++
 3 files changed, 70 insertions(+), 11 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/powerpc/pr108338.c

diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index a16ee30f0c061965da07a5832097eeffa6ccf29c..94b948868881b1a96c5653cbc396b81ebb60c74c 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -2101,3 +2101,8 @@ (define_predicate "macho_pic_address"
   else
     return false;
 })
+
+(define_predicate "lowpart_subreg_operator"
+  (and (match_code "subreg")
+       (match_test "subreg_lowpart_offset (mode, GET_MODE (SUBREG_REG (op)))
+		    == SUBREG_BYTE (op)")))
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index b0db8ae508d8ee50e34f85b654988ae0919e152f..1a8f3ff362a3973ec6260a0702fa930679cf66d1 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -8215,13 +8215,24 @@ (define_insn_and_split "movsf_from_si"
 {
   rtx op0 = operands[0];
   rtx op1 = operands[1];
-  rtx op2 = operands[2];
-  rtx op1_di = gen_rtx_REG (DImode, REGNO (op1));
 
-  /* Move SF value to upper 32-bits for xscvspdpn.  */
-  emit_insn (gen_ashldi3 (op2, op1_di, GEN_INT (32)));
-  emit_insn (gen_p8_mtvsrd_sf (op0, op2));
-  emit_insn (gen_vsx_xscvspdpn_directmove (op0, op0));
+  if (TARGET_P9_VECTOR)
+    {
+      rtx op0_v = gen_rtx_REG (V4SImode, REGNO (op0));
+      emit_insn (gen_vsx_splat_v4si (op0_v, op1));
+      emit_insn (gen_vsx_xscvspdpn_directmove (op0, op0));
+    }
+  else
+    {
+      rtx op2 = operands[2];
+      rtx op1_di = gen_rtx_REG (DImode, REGNO (op1));
+
+      /* Move SF value to upper 32-bits for xscvspdpn.  */
+      emit_insn (gen_ashldi3 (op2, op1_di, GEN_INT (32)));
+      emit_insn (gen_p8_mtvsrd_sf (op0, op2));
+      emit_insn (gen_vsx_xscvspdpn_directmove (op0, op0));
+    }
+
   DONE;
 }
   [(set_attr "length"
@@ -8234,18 +8245,19 @@ (define_insn_and_split "movsf_from_si"
 	    "*,          *,         p9v,       p8v,       *,         *,
 	     p8v,        p8v,       p8v,       *")])
 
+(define_code_iterator any_rshift [ashiftrt lshiftrt])
+
 ;; For extracting high part element from DImode register like:
 ;;     {%1:SF=unspec[r122:DI>>0x20#0] 86;clobber scratch;}
 ;; split it before reload with "and mask" to avoid generating shift right
 ;; 32 bit then shift left 32 bit.
-(define_insn_and_split "movsf_from_si2"
+(define_insn_and_split "movsf_from_si2_<code>"
   [(set (match_operand:SF 0 "gpc_reg_operand" "=wa")
 	    (unspec:SF
-	     [(subreg:SI
-	       (ashiftrt:DI
+	     [(match_operator:SI 3 "lowpart_subreg_operator"
+	       [(any_rshift:DI
 		(match_operand:DI 1 "input_operand" "r")
-		(const_int 32))
-	       0)]
+		(const_int 32))])]
 	     UNSPEC_SF_FROM_SI))
   (clobber (match_scratch:DI 2 "=r"))]
   "TARGET_NO_SF_SUBREG"
diff --git a/gcc/testsuite/gcc.target/powerpc/pr108338.c b/gcc/testsuite/gcc.target/powerpc/pr108338.c
new file mode 100644
index 0000000000000000000000000000000000000000..39da7cec535c59ec34d5f6fc4a63b44ef4316976
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr108338.c
@@ -0,0 +1,42 @@
+// { dg-do run }
+// { dg-options "-O2 -save-temps" }
+
+float __attribute__ ((noipa)) sf_from_di_off0 (long long l)
+{
+  char buff[16];
+  *(long long*)buff = l;
+  float f = *(float*)(buff);
+  return f;    
+}
+
+float  __attribute__ ((noipa)) sf_from_di_off4 (long long l)
+{
+  char buff[16];
+  *(long long*)buff = l;
+  float f = *(float*)(buff + 4);
+  return f; 
+}
+
+/* Under lp64, parameter 'l' is in one DI reg, then bitcast sub DI to SF. */
+/* { dg-final { scan-assembler-times {\mrldicr\M} 1 { target { lp64 && has_arch_pwr8 } } } } */
+/* { dg-final { scan-assembler-times {\mxscvspdpn\M} 2 { target { lp64 && has_arch_pwr8 } } } } */
+
+/* { dg-final { scan-assembler-times {\mmtvsrd\M} 2 { target { lp64 && { has_arch_pwr8 && { ! has_arch_pwr9 } } } } } } */
+/* { dg-final { scan-assembler-times {\mmtvsrd\M} 1 { target { lp64 && has_arch_pwr9 } } } } */
+/* { dg-final { scan-assembler-times {\mmtvsrws\M} 1 { target { lp64 && has_arch_pwr9 } } } } */
+
+union di_sf_sf
+{
+  struct {float f1; float f2;};
+  long long l;
+};
+
+int main()
+{
+  union di_sf_sf v;
+  v.f1 = 1.0f;
+  v.f2 = 2.0f;
+  if (sf_from_di_off0 (v.l) != 1.0f || sf_from_di_off4 (v.l) != 2.0f )
+    __builtin_abort ();
+  return 0;
+}
-- 
2.39.3